© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 6519
    Prev
    Next
    INDEX
    Explanations

    errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quantified
    -0.09
     contemplation
    -0.08
     stilte
    -0.08
    setw
    -0.08
    .Serialize
    -0.08
     संख्या
    -0.08
    _Equals
    -0.08
     quantidade
    -0.08
    édito
    -0.08
     spørg
    -0.08
    POSITIVE LOGITS
     errors
    0.21
    errors
    0.20
    (errors
    0.20
    	errors
    0.19
    Errors
    0.18
    .errors
    0.17
    _errors
    0.17
     Errors
    0.17
    _ERRORS
    0.15
    .Errors
    0.14
    Activations Density 0.002%

    No Known Activations